Skip to main content
Glama
mcp-cisco-support

mcp-cisco-support

by sieteunoseis

Search Cisco security advisories

psirt_search
Read-only

Find Cisco security advisories by OS and version to check if a release is vulnerable, returning applicable advisories and first fixed releases.

Instructions

Find Cisco security advisories. Use os_type + version to answer "is this software version vulnerable?" (returns advisories affecting that release with first fixed releases). Other modes: product, severity, year, latest, or a first-published date range.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "psirt_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number (see paging.next_page in the result).
yearNoPublication year
latestNoMost recent N advisories
os_typeNoOperating system, used with version
productNoProduct name to match, e.g. "Cisco Unified Communications Manager"
versionNoRelease for os_type, e.g. "17.9.4" or "17.15.4b"
severityNo
page_sizeNo
response_formatNoconcise (default) returns key fields only; detailed adds descriptions, notes and secondary fields.concise
first_published_toNoYYYY-MM-DD
first_published_fromNoYYYY-MM-DD, with first_published_to

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.0.0

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, and the description adds that results include first fixed releases, which is genuinely useful beyond the annotations. It says nothing about result volume, ordering, or that paging is handled via paging.next_page in the response, so the bar for a read-only search is met only partially.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with no filler: the identity first, the highest-value use case second, the remaining modes third. Everything is front-loaded where an agent will read it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-param, zero-required, no-output-schema search tool, the description covers the primary invocation path and names the remaining filter modes. Paging and response_format details are left to the schema, which is acceptable since those fields are self-describing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 82%, so the schema already carries the parameter burden and a 3 is the baseline. The description adds a little by framing os_type+version as a paired filter that yields affected releases plus fixed versions, but it does not explain how the mode parameters interact or whether they combine or override each other.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Find Cisco security advisories") and enumerates the search modes it supports. It never distinguishes itself from the sibling psirt_get, so an agent must infer that this is the discovery tool and that is the fetch-by-id tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete task-oriented trigger ("Use os_type + version to answer 'is this software version vulnerable?'") and lists the alternative search modes. It stops short of stating when not to use it or pointing to psirt_get for single-advisory retrieval.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.